Computer Rating System Prediction Results for College Football (NCAA IA)

2014 Season Totals

Through 2014-12-15
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Thompson CAL0.752780.5042912.54461.1715251.001720542178353347
2Line (updated)0.750350.5313112.41751.3703248.485721541180263232
3Thompson ATS0.750000.5014312.60250.9253253.443720540180351349
4DP Dwiggins0.749350.4517913.67621.4726293.43038328796164199
5Computer Adjusted Line0.748960.5174312.45281.3003249.153721540181282263
6Dokter Entropy0.746190.4928612.75341.3483257.329721538183345355
7Sagarin Ratings0.746190.4885713.07411.2879271.260721538183342358
8CPA Rankings0.746190.5049913.23760.4191273.868721538183354347
9Billingsley+0.744800.5221113.15830.4496279.300721537184366335
10Line (Midweek)0.7447112.44711.3032251.113709528181
11Thompson Average0.744440.4985612.68361.0568256.837720536184347349
12System Median0.742020.5101712.81650.8753261.307721535186351337
13DirectorOfInformation0.740640.4978613.00880.6128270.923721534187349352
14Pigskin Index0.740640.5113512.96120.5926268.179721534187338323
15Sagarin Points0.739250.4828613.01171.3596272.241721533188338362
16Stat Fox0.739250.4940713.39391.8741286.775721533188333341
17Dave Congrove0.739250.4864513.78370.4058307.981721533188341360
18Sagarin Golden Mean0.737860.4978613.39351.1960281.312721532189349352
19Line (opening)0.737130.5256012.50070.9903250.434719530189308278
20Atomic Football0.736480.5074912.87901.2232264.594721531190339329
21Pi-Rate Ratings0.736480.5386812.92671.0220269.223721531190376322
22Dunkel Index0.735380.5071613.57471.3974305.049718528190354344
23Massey Consensus0.735090.5121313.23881.1711277.993721530191359342
24System Average0.735090.5021512.84580.8679262.722721530191351348
25Ashby AccuRatings0.735090.4984812.78640.7838260.357721530191327329
26Payne Power Ratings0.734720.5150213.37630.4093283.492720529191360339
27Randal Horobik0.734350.4780213.73601.1337291.875591434157261285
28Catherwood Ratings0.732960.5044513.66761.5814296.393719527192340334
29Edward Kambour0.730990.5014513.32131.1606282.489710519191346344
30PI-Rate Bias0.730930.5330512.90820.9202266.523721527194371325
31ARGH Power Ratings0.730930.4933113.53851.0863286.316721527194332341
32Brent Craig 20.730880.4781313.29414.5184281.04835325895164179
33Pi-Ratings Mean0.729540.5389012.77240.6820259.737721526195374320
34Billingsley0.729540.5206813.58120.0879299.752721526195365336
35Regression Based Analys0.728730.4741413.94222.3660311.432623454169275305
36Sagarin Points Elo0.728160.5043013.52671.1812289.949721525196352346
37Moore Power Ratings0.725630.4820713.71601.2407299.430718521197336361
38Tempo Free Gridiron0.723920.5302013.6453-1.1541309.576623451172316280
39Nutshell Girl0.723280.4766213.75780.9407303.877683494189316347
40Lee Burdorf0.723230.4942513.65890.8632293.494719520199344352
41Born Power Index0.722610.4935813.95550.9243304.865721521200346355
42Laz Index0.721220.5035713.25090.3266277.343721520201353348
43Daniel Curry Index0.720830.4985714.38900.8935328.127720519201348350
44Cleanup Hitter0.719700.5007814.24242.5109340.461660475185320319
45Keeper0.719440.4842913.78892.1595294.124720518202339361
46ComPughter Ratings0.719050.4992813.31780.4858279.581719517202349350
47NutShell Combo0.719040.5057713.44780.5223291.764541389152263257
48NutShell Sports0.717660.5072914.05110.1132319.806719516203348338
49Stephen Kerns0.717360.4827613.7957-0.0097295.507697500197322345
50Brent Craig0.715280.4821213.52861.4006285.506720515205337362
51ThePowerRank.com0.714080.5007313.10160.5018274.560703502201342341
52Massey Ratings0.713300.5047313.2953-0.0294283.514579413166267262
53MDS Model0.712730.4968114.00070.2210312.442644459185311315
54Howell0.711110.5059913.69520.7188296.954720512208338330
55Marsee0.710120.4780114.00972.7642309.436721512209326356
56Covers.com0.710120.5251813.7367-0.1530304.835721512209365330
57PerformanZ Ratings0.708740.4992913.90550.7865304.027721511210350351
58Beck Elo0.707830.4845213.75790.9120293.992664470194313333
59Laffaye RWP0.707350.5406613.9103-1.5732313.079721510211379322
60Donchess Inference0.706540.5028713.47710.2268287.394719508211351347
61Linear Regression0.706060.5031413.5759-0.7334289.35433023397160158
62Bihl System0.700700.4868113.54971.2432284.811431302129203214
63Laffaye XWP0.700420.4792016.44046.6307420.933721505216334363
64Loudsound.org0.700000.5537213.5815-3.3284305.866380266114201162
65Super List0.699030.5285714.64140.9806339.574721504217370330
66Nutshell Eye0.698710.5048713.53640.7253294.448541378163259254
67CPA Retro0.696260.4893014.27010.2315314.848721502219343358
68FEI Projections0.695830.5118313.76110.2111302.378720501219346330
69Logistic Regression0.693940.5597515.9484-3.0864399.338330229101178140
70Sportrends0.693650.5092114.39840.0000335.483630437193304293
71Least Squares w/ HFA0.684850.5566015.2223-0.5413369.493330226104177141
72PointShare0.665430.5144513.8699-0.1282303.097541360181267252

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases